© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163752
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (
    0.49
    로
    0.48
    Para
    0.48
    0.47
    |
    0.47
    PI
    0.46
     agonists
    0.46
     generalizes
    0.46
    부
    0.46
     along
    0.45
    POSITIVE LOGITS
    ::$
    0.54
    NESDAY
    0.52
     Над
    0.52
     над
    0.50
     रवाना
    0.50
     သင်
    0.50
     EnglishChoose
    0.50
     hechas
    0.50
    艙
    0.50
     weaken
    0.49
    Activations Density 0.000%

    No Known Activations